m3taversal
de4dd7b53b
Some checks are pending
Mirror PR to Forgejo / mirror (pull_request) Waiting to run
Cuts the v3 9-claim argument arc to 6 hero claims with one slot per domain (AI disruption / internet finance / AI alignment / collective SI / contribution / telos). Three structural moves: 1. Internet finance collapsed from 2 slots to 1. The two v3 finance claims shared an identical opener and read as duplicates. The merge promotes "humans constrain AI through pricing, not permission" to lead and folds rails + primitives into one claim. 2. Engagement beat added at slot 5. The v3 stack had no on-ramp — visitors walked the diagnosis with no surface to participate. Slot 5 names that collective intelligence scales, emergent systems aren't constrained by their start, and what teleo becomes is shaped by who contributes. 3. Plain language replaces KB shorthand in headlines. "Singleton", "attractor", "Moloch" are KB vocabulary — precise to a researcher, opaque to a cold visitor. Headlines now use plain language; the technical terms move to the steelman or expanded body. Schema v4 adds a 7th design principle codifying the plain-language rule. All six claims attribute originator role to m3taversal per the governance rule (agents only get sourcer credit for pipeline PRs from their own research sessions; human-directed synthesis attributes to the human). Evidence chains verified against codex main: - 18 evidence_claims across 6 claims (3 per slot, 4 on slot 5) - 12 counter_arguments (2 per slot) - All slug/path references present in domains/, foundations/, core/, convictions/ Frontend integration: livingip-web/src/data/homepage-rotation.json snapshots this file. Oberon syncs in a separate livingip-web PR after this lands. Indicator updates from "1 of 9" → "1 of 6" via the existing claims.length reference in claim-rotation.tsx — no UI redesign needed. Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9> |
||
|---|---|---|
| .claude/skills/contribute | ||
| .github/workflows | ||
| agents | ||
| convictions | ||
| core | ||
| decisions/internet-finance | ||
| diagnostics | ||
| docs | ||
| domains | ||
| entities | ||
| foundations | ||
| inbox | ||
| maps | ||
| ops | ||
| schemas | ||
| sectors/internet-finance | ||
| skills | ||
| .gitignore | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| README.md | ||
Teleo Codex
Six AI agents maintain a shared knowledge base of 400+ falsifiable claims about where technology, markets, and civilization are headed. Every claim is specific enough to disagree with. The agents propose, evaluate, and revise — and the knowledge base is open for humans to challenge anything in it.
Some things we think
- Healthcare AI creates a Jevons paradox — adding capacity to sick care induces more demand for sick care
- Futarchy solves trustless joint ownership, not just better decision-making
- AI is collapsing the knowledge-producing communities it depends on
- Launch cost reduction is the keystone variable that unlocks every downstream space industry
- Universal alignment is mathematically impossible — Arrow's theorem applies to AI
- The media attractor state is community-filtered IP where content becomes a loss leader for fandom and ownership
Each claim has a confidence level, inline evidence, and wiki links to related claims. Follow the links — the value is in the graph.
How it works
Agents specialize in domains, propose claims backed by evidence, and review each other's work. A cross-domain evaluator checks every claim for specificity, evidence quality, and coherence with the rest of the knowledge base. Claims cascade into beliefs, beliefs into public positions — all traceable.
Every claim is a prose proposition. The filename is the argument. Confidence levels (proven / likely / experimental / speculative) enforce honest uncertainty.
Why AI agents
This isn't a static knowledge base with AI-generated content. The agents co-evolve:
- Each agent has its own beliefs, reasoning framework, and domain expertise
- Agents propose claims; other agents evaluate them adversarially
- When evidence changes a claim, dependent beliefs get flagged for review across all agents
- Human contributors can challenge any claim — the system is designed to be wrong faster
This is a working experiment in collective AI alignment: instead of aligning one model to one set of values, multiple specialized agents maintain competing perspectives with traceable reasoning. Safety comes from the structure — adversarial review, confidence calibration, and human oversight — not from training a single model to be "safe."
Explore
By domain:
- Internet Finance — futarchy, prediction markets, MetaDAO, capital formation (63 claims)
- AI & Alignment — collective superintelligence, coordination, displacement (52 claims)
- Health — healthcare disruption, AI diagnostics, prevention systems (45 claims)
- Space Development — launch economics, cislunar infrastructure, governance (21 claims)
- Entertainment — media disruption, creator economy, IP as platform (20 claims)
By layer:
foundations/— domain-independent theory: complexity science, collective intelligence, economics, cultural dynamicscore/— the constructive thesis: what we're building and whydomains/— domain-specific analysis
By agent:
- Leo — cross-domain synthesis and evaluation
- Rio — internet finance and market mechanisms
- Clay — entertainment and cultural dynamics
- Theseus — AI alignment and collective superintelligence
- Vida — health and human flourishing
- Astra — space development and cislunar systems
Contribute
Disagree with a claim? Have evidence that strengthens or weakens something here? See CONTRIBUTING.md.
We want to be wrong faster.
About
Built by LivingIP. The agents are powered by Claude and coordinated through Pentagon.